Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED)

Danilo Šćepanović, Joshua Kirshtein, Ameet Kumar Jain, Russell H Taylor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The registration of preoperative CT to intra-operative reality systems is a crucial step in Computer Assisted Orthopedic Surgery (CAOS). The intra-operative sensors include 3D digitizers, fiducials, X-rays and Ultrasound (US). FAPBED is designed to process CT volumes for registration to tracked US data. Tracked US is advantageous because it is real time, noninvasive, and non-ionizing, but it is also known to have inherent inaccuracies which create the need to develop a framework that is robust to various uncertainties, and can be useful in US-CT registration. Furthermore, conventional registration methods depend on accurate and absolute segmentation. Our proposed probabilistic framework addresses the segmentation-registration duality, wherein exact segmentation is not a prerequisite to achieve accurate registration. In this paper, we develop a method for fast and automatic probabilistic bone surface (edge) detection in CT images. Various features that influence the likelihood of the surface at each spatial coordinate are combined using a simple probabilistic framework, which strikes a fair balance between a high-level understanding of features in an image and the low-level number crunching of standard image processing techniques. The algorithm evaluates different features for detecting the probability of a bone surface at each voxel, and compounds the results of these methods to yield a final, low-noise, probability map of bone surfaces in the volume. Such a probability map can then be used in conjunction with a similar map from tracked intra-operative US to achieve accurate registration. Eight sample pelvic CT scans were used to extract feature parameters and validate the final probability maps. An un-optimized fully automatic Matlab code runs in five minutes per CT volume on average, and was validated by comparison against hand-segmented gold standards. The mean probability assigned to nonzero surface points was 0.8, while nonzero non-surface points had a mean value of 0.38 indicating clear identification of surface points on average. The segmentation was also sufficiently crisp, with a full width at half maximum (FWHM) value of 1.51 voxels.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
EditorsJ.M. Fitzpatrick, J.M. Reinhardt
Pages1753-1765
Number of pages13
Volume5747
EditionIII
DOIs
StatePublished - 2005
EventMedical Imaging 2005 - Image Processing - San Diego, CA, United States
Duration: Feb 13 2005Feb 17 2005

Other

OtherMedical Imaging 2005 - Image Processing
CountryUnited States
CitySan Diego, CA
Period2/13/052/17/05

Fingerprint

Edge detection
Bone
Ultrasonics
Computerized tomography
Orthopedics
Full width at half maximum
Surgery
Image processing
X rays
Sensors

Keywords

  • Automatic
  • Bone
  • CT
  • Image Registration
  • Probabilistic
  • Segmentation
  • Ultrasound

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Šćepanović, D., Kirshtein, J., Jain, A. K., & Taylor, R. H. (2005). Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED). In J. M. Fitzpatrick, & J. M. Reinhardt (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE (III ed., Vol. 5747, pp. 1753-1765). [204] https://doi.org/10.1117/12.596950

Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED). / Šćepanović, Danilo; Kirshtein, Joshua; Jain, Ameet Kumar; Taylor, Russell H.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. ed. / J.M. Fitzpatrick; J.M. Reinhardt. Vol. 5747 III. ed. 2005. p. 1753-1765 204.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Šćepanović, D, Kirshtein, J, Jain, AK & Taylor, RH 2005, Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED). in JM Fitzpatrick & JM Reinhardt (eds), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. III edn, vol. 5747, 204, pp. 1753-1765, Medical Imaging 2005 - Image Processing, San Diego, CA, United States, 2/13/05. https://doi.org/10.1117/12.596950
Šćepanović D, Kirshtein J, Jain AK, Taylor RH. Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED). In Fitzpatrick JM, Reinhardt JM, editors, Progress in Biomedical Optics and Imaging - Proceedings of SPIE. III ed. Vol. 5747. 2005. p. 1753-1765. 204 https://doi.org/10.1117/12.596950
Šćepanović, Danilo ; Kirshtein, Joshua ; Jain, Ameet Kumar ; Taylor, Russell H. / Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED). Progress in Biomedical Optics and Imaging - Proceedings of SPIE. editor / J.M. Fitzpatrick ; J.M. Reinhardt. Vol. 5747 III. ed. 2005. pp. 1753-1765
@inproceedings{ba5d313e452644db9190dfde3b3dedcf,
title = "Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED)",
abstract = "The registration of preoperative CT to intra-operative reality systems is a crucial step in Computer Assisted Orthopedic Surgery (CAOS). The intra-operative sensors include 3D digitizers, fiducials, X-rays and Ultrasound (US). FAPBED is designed to process CT volumes for registration to tracked US data. Tracked US is advantageous because it is real time, noninvasive, and non-ionizing, but it is also known to have inherent inaccuracies which create the need to develop a framework that is robust to various uncertainties, and can be useful in US-CT registration. Furthermore, conventional registration methods depend on accurate and absolute segmentation. Our proposed probabilistic framework addresses the segmentation-registration duality, wherein exact segmentation is not a prerequisite to achieve accurate registration. In this paper, we develop a method for fast and automatic probabilistic bone surface (edge) detection in CT images. Various features that influence the likelihood of the surface at each spatial coordinate are combined using a simple probabilistic framework, which strikes a fair balance between a high-level understanding of features in an image and the low-level number crunching of standard image processing techniques. The algorithm evaluates different features for detecting the probability of a bone surface at each voxel, and compounds the results of these methods to yield a final, low-noise, probability map of bone surfaces in the volume. Such a probability map can then be used in conjunction with a similar map from tracked intra-operative US to achieve accurate registration. Eight sample pelvic CT scans were used to extract feature parameters and validate the final probability maps. An un-optimized fully automatic Matlab code runs in five minutes per CT volume on average, and was validated by comparison against hand-segmented gold standards. The mean probability assigned to nonzero surface points was 0.8, while nonzero non-surface points had a mean value of 0.38 indicating clear identification of surface points on average. The segmentation was also sufficiently crisp, with a full width at half maximum (FWHM) value of 1.51 voxels.",
keywords = "Automatic, Bone, CT, Image Registration, Probabilistic, Segmentation, Ultrasound",
author = "Danilo Šćepanović and Joshua Kirshtein and Jain, {Ameet Kumar} and Taylor, {Russell H}",
year = "2005",
doi = "10.1117/12.596950",
language = "English (US)",
volume = "5747",
pages = "1753--1765",
editor = "J.M. Fitzpatrick and J.M. Reinhardt",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "III",

}

TY - GEN

T1 - Fast Algorithm for Probabilistic Bone Edge Detection (FAPBED)

AU - Šćepanović, Danilo

AU - Kirshtein, Joshua

AU - Jain, Ameet Kumar

AU - Taylor, Russell H

PY - 2005

Y1 - 2005

N2 - The registration of preoperative CT to intra-operative reality systems is a crucial step in Computer Assisted Orthopedic Surgery (CAOS). The intra-operative sensors include 3D digitizers, fiducials, X-rays and Ultrasound (US). FAPBED is designed to process CT volumes for registration to tracked US data. Tracked US is advantageous because it is real time, noninvasive, and non-ionizing, but it is also known to have inherent inaccuracies which create the need to develop a framework that is robust to various uncertainties, and can be useful in US-CT registration. Furthermore, conventional registration methods depend on accurate and absolute segmentation. Our proposed probabilistic framework addresses the segmentation-registration duality, wherein exact segmentation is not a prerequisite to achieve accurate registration. In this paper, we develop a method for fast and automatic probabilistic bone surface (edge) detection in CT images. Various features that influence the likelihood of the surface at each spatial coordinate are combined using a simple probabilistic framework, which strikes a fair balance between a high-level understanding of features in an image and the low-level number crunching of standard image processing techniques. The algorithm evaluates different features for detecting the probability of a bone surface at each voxel, and compounds the results of these methods to yield a final, low-noise, probability map of bone surfaces in the volume. Such a probability map can then be used in conjunction with a similar map from tracked intra-operative US to achieve accurate registration. Eight sample pelvic CT scans were used to extract feature parameters and validate the final probability maps. An un-optimized fully automatic Matlab code runs in five minutes per CT volume on average, and was validated by comparison against hand-segmented gold standards. The mean probability assigned to nonzero surface points was 0.8, while nonzero non-surface points had a mean value of 0.38 indicating clear identification of surface points on average. The segmentation was also sufficiently crisp, with a full width at half maximum (FWHM) value of 1.51 voxels.

AB - The registration of preoperative CT to intra-operative reality systems is a crucial step in Computer Assisted Orthopedic Surgery (CAOS). The intra-operative sensors include 3D digitizers, fiducials, X-rays and Ultrasound (US). FAPBED is designed to process CT volumes for registration to tracked US data. Tracked US is advantageous because it is real time, noninvasive, and non-ionizing, but it is also known to have inherent inaccuracies which create the need to develop a framework that is robust to various uncertainties, and can be useful in US-CT registration. Furthermore, conventional registration methods depend on accurate and absolute segmentation. Our proposed probabilistic framework addresses the segmentation-registration duality, wherein exact segmentation is not a prerequisite to achieve accurate registration. In this paper, we develop a method for fast and automatic probabilistic bone surface (edge) detection in CT images. Various features that influence the likelihood of the surface at each spatial coordinate are combined using a simple probabilistic framework, which strikes a fair balance between a high-level understanding of features in an image and the low-level number crunching of standard image processing techniques. The algorithm evaluates different features for detecting the probability of a bone surface at each voxel, and compounds the results of these methods to yield a final, low-noise, probability map of bone surfaces in the volume. Such a probability map can then be used in conjunction with a similar map from tracked intra-operative US to achieve accurate registration. Eight sample pelvic CT scans were used to extract feature parameters and validate the final probability maps. An un-optimized fully automatic Matlab code runs in five minutes per CT volume on average, and was validated by comparison against hand-segmented gold standards. The mean probability assigned to nonzero surface points was 0.8, while nonzero non-surface points had a mean value of 0.38 indicating clear identification of surface points on average. The segmentation was also sufficiently crisp, with a full width at half maximum (FWHM) value of 1.51 voxels.

KW - Automatic

KW - Bone

KW - CT

KW - Image Registration

KW - Probabilistic

KW - Segmentation

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=23844516180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23844516180&partnerID=8YFLogxK

U2 - 10.1117/12.596950

DO - 10.1117/12.596950

M3 - Conference contribution

AN - SCOPUS:23844516180

VL - 5747

SP - 1753

EP - 1765

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

A2 - Fitzpatrick, J.M.

A2 - Reinhardt, J.M.

ER -